SYSTEM AND METHOD FOR PREDICTIVE MAINTENANCE OF AQUATIC FACILITY

Abstract

TITLE OF THE INVENTION: SYSTEM AND METHOD FOR PREDICTIVE MAINTENANCE OF AN AQUATIC FACILITY The predictive maintenance system for an aquatic facility (100) comprises: - at least one physical / chemical sensor (110, 115, 116, 117, 181, 182, 183, 184) interacting with the water in at least one aquatic facility and configured to provide a series of at least one detected value representative of a physical / chemical parameter, and - at least one processor (120) configured to execute instructions representative of the following steps: - operation of a trained machine learning model, said model being trained to associate, for at least one series of detected values ​​representative of a physical / chemical parameter,at least one operational degradation event of an aquatic facility on a date of occurrence of the event and - determination of a sequence of maintenance operations to be carried out on at least one aquatic facility based on at least one planned operational degradation event of an aquatic facility and the associated date of occurrence of the event. Figure for the abbreviation: Figure 1,

Description

Title of the invention: SYSTEM AND METHOD FOR PREDICTIVE MAINTENANCE OF AQUATIC INSTALLATIONS Technical field of the invention

[0001] The present invention relates to a predictive maintenance system for aquatic installations and a method for predictive maintenance of aquatic installations. It is particularly applicable to the field of physical and chemical water treatment and to the field of in-situ physical and chemical water treatment. The present invention is applicable to commercial and residential recreational aquatic activities (swimming pools, spas, splash pads, water features, fountains, water parks, wellness facilities, therapy facilities, lazy rivers, etc.) and to any similar sector or market segment where water is treated and / or monitored in a semi-closed and / or closed circuit (such as wastewater, water recycling, industrial water, drinking water, animal water, etc.).) and to any similar sector or market segment where water is used as part of the process (such as evaporative cooling for power generation and data centers, heating, ventilation and air conditioning, and management of stored water for fire suppression, etc.). State of the art

[0002] The approaches described in this section are approaches that can be pursued, but not necessarily approaches that have been conceived or pursued previously. Therefore, unless otherwise indicated, it should not be presumed that all the approaches described in this section are considered to be part of the prior art simply because they are included in this section.

[0003] In current digital systems for controlling and monitoring aquatic installations, such as swimming pool control and monitoring systems, alerts related to maintenance needs for such installations are issued based on the value of an operational parameter of a component associated with the aquatic installation and a corresponding alert threshold. Such an operational parameter might correspond, for example, to the need to replace an empty consumable in the installation, to clean the installation and / or the filter, or to perform maintenance on a circulation pump.

[0004] Such systems operate on an element-by-element basis and are linear in their modes of operation, since they are limited to the comparison of a operational parameter value at a threshold to determine a need for intervention and / or maintenance.

[0005] However, the operational parameters of aquatic facilities interact with each other, making linear control and monitoring systems inaccurate, since an aquatic facility situation can deteriorate more rapidly than predicted by traditional, linear control and monitoring systems. To compensate for such shortcomings, alert threshold values ​​are usually adjusted, leading to earlier than necessary alerts and, in the worst-case scenario, to users failing to heed these alerts, which may be considered overly conservative.

[0006] Furthermore, such systems typically stop at issuing alerts, and the actual maintenance of the aquatic installation is handled outside of these systems. Consequently, maintenance may or may not be performed, and this does not interact with these systems in any way other than the fact that the monitored value may or may not trigger an alert if the cause of the alert has been properly maintained.

[0007] All these systems are therefore unsatisfactory in terms of the punctuality and accuracy of the maintenance of aquatic installations, as well as in terms of the ability to monitor the condition and maintenance operations related to an aquatic installation or a set of such aquatic installations, and in terms of the ability to manage the needs and use of consumable resources to maintain an ideal state of the water in accordance with the user and / or operator setpoints (such as energy consumption, water consumption and consumption for associated chemical treatment).For users responsible for dozens or hundreds of these aquatic facilities, these problems worsen, generating significant time losses for the maintenance operator, also considerably increasing the risk that maintenance requirements will not be met on time, leading to a risk to the health and safety of users and maintenance personnel and permanent degradation of the aquatic facilities, as well as a considerable increase in operating costs with an excess of needs and / or use of consumable resources to maintain an ideal water condition in accordance with user and / or operator setpoints (such as energy consumption, water consumption and consumption for associated chemical treatment). Summary of the invention

[0008] The present invention aims to overcome the aforementioned disadvantages as well as other disadvantages that could be overcome, although not mentioned in the description below.

[0009] The inventors have discovered that the use of a machine learning model trained to predict the risk of occurrence of a negative and / or damaging event and / or an increase in the use and / or need for consumables (such as energy consumption, water consumption and consumption for associated chemical treatment) in an aquatic facility, either in relation to the water of the facility and / or the facilities themselves and / or the installed equipment, combined with a capacity for planning maintenance tasks, enables proactive and optimized maintenance in terms of time and / or cost, this model also being used to predict risks to the health and safety of users and maintenance technicians.

[0010] Such a machine learning model can be trained on a variety of data, both internal to the water or the installation and external.

[0011] Such data can come from a variety of sensors and data sources.

[0012] Such sensors can in particular be integrated into installed equipment and floating and / or submersible mobile vehicles, which operate within aquatic installations.

[0013] Such sensors may in particular correspond to specific devices for measuring total alkalinity.

[0014] Such data sources may in particular correspond to network and Internet databases and data sources. Brief description of the drawings

[0015] Other advantages, objectives and special features of the invention will become clear from the following non-exhaustive description of at least one particular system and method of the present invention, in conjunction with the accompanying drawings, in which:

[0016] Figure [1] schematically represents a particular embodiment of a system that is the subject of the present invention,

[0017] [Fig.2] schematically represents, in the form of a flowchart, a first particular sequence of steps of a process which is the subject of the present invention,

[0018] [Fig.3] schematically represents a particular embodiment of a submersible vehicle used in the system which is the subject of the present invention,

[0019] Figure 4 schematically represents a particular embodiment of a floating vehicle used in the system that is the subject of the present invention.

[0020] Figure 5 schematically represents a first view of a particular sensor that can be used in the system that is the subject of the present invention,

[0021] Figure 6 schematically represents a second view of a particular sensor that can be used in the system that is the subject of the present invention.

[0022] Figure 7 schematically represents a graph showing a succession of pH measurements at the boundary layer of a water mass for different values ​​of total alkalinity,

[0023] Figure 8 represents, schematically and in the form of a flowchart, a second particular sequence of steps of a process that is the subject of the present invention, and

[0024] [Fig.9] schematically represents a computer system capable of carrying out a process which is the subject of the present invention. Detailed description

[0025] This description is not exhaustive, because each feature of one embodiment can be advantageously combined with any other feature of any other embodiment.

[0026] Various inventive concepts can be realized in the form of one or more processes, an example of which has been provided. The steps performed as part of the process can be ordered in any suitable manner. Therefore, it is possible to design embodiments in which steps are performed in a different order than that illustrated, which may include the simultaneous performance of certain steps, even if they are represented as sequential steps in illustrative embodiments.

[0027] The expression "and / or" as used herein in the specification and in the claims shall be understood as meaning "either or both" of the elements thus combined, that is to say, elements which are present conjunctively in some cases and disjunctively in others. Several elements listed with "and / or" shall be interpreted in the same way, that is to say, as "one or more" of the elements thus combined. Other elements besides those specifically identified by the "and / or" clause may optionally be present, whether or not they are related to those specifically identified elements.Thus, by way of non-limiting example, a reference to "A and / or B", when used in conjunction with an open language such as "including", may refer, in one embodiment, to A only (optionally including elements other than B); in another embodiment, to B only (optionally including elements other than A); in yet another embodiment, to both A and B (optionally including other elements); etc.

[0028] As used herein in the specification and in the claims, "or" should be understood as having the same meaning as "and / or" as defined above. For example, when separating elements in a list, "or" or "and / or" should be interpreted as inclusive, that is, as including at least one element, but also including several from a number or list of elements, and optionally, other elements not listed in the list.

[0029] As used herein in the specification and in the claims, the expression "at least one," with reference to a list of one or more elements, is to be understood as meaning at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each element specifically listed in the list of elements and not excluding any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements to which the phrase "at least one" refers, whether or not they are related to those specifically identified elements.Thus, by way of non-limiting example, "at least one of A and B" (or, equivalently, "at least one of A or B" or equivalently, "at least one of A and / or B") may refer, in one embodiment, to at least one, optionally including more than one, A, without B present (and optionally including elements other than B); in another embodiment, to at least one, optionally including more than one, B, without A present (and optionally including elements other than A); in yet another embodiment, to at least one, optionally including more than one, A, and to at least one, optionally including more than one, B (and optionally including other elements); etc.

[0030] In the claims, as well as in the above descriptive memorandum, all transitional expressions such as "comprising", "including", "carrying", "having", "containing", "implying", "holding", "composed of", and the like should be understood as open-ended, i.e., as including, but not limited to. Only the transitional expressions "consisting of" and "consisting essentially of" should be understood as closed or semi-closed transitional expressions, respectively.

[0031] According to at least one embodiment, the techniques described herein are implemented by at least one computing device. The techniques may be implemented in whole or in part using a combination of at least one server computer and / or other computing devices that are coupled using a network, such as a packet data network. The computing devices may be hardwired to perform the techniques or may include digital electronic devices such as at least one application-specific integrated circuit (ASIC) or a user-programmable pre-broadcast array (FPGA) that is programmed persistently perform the techniques or may include at least one general-purpose hardware processor programmed to perform the techniques according to program instructions in firmware, memory, other storage, or a combination thereof. Such computing devices may also combine custom hardwired logic, ASICs, or FPGAs with custom programming to accomplish the described techniques.Computing devices can be server computers, workstations, personal computers, portable computing systems, handheld devices, mobile computing devices, wearable devices, body-mounted or implantable devices, smartphones, smart devices, network interconnection devices, autonomous or semi-autonomous devices such as robots or unmanned ground or air vehicles, any other electronic device that incorporates hardwired and / or program logic to implement the techniques described, one or more virtual computing machines or instances in a data center and / or a network of server computers and / or personal computers.

[0032] According to at least one embodiment, the present invention uses software, stored as instructions in a memory, ROM, or storage unit, which may comprise one or more sets of instructions organized into modules, processes, objects, functions, routines, or calls. The instructions may be organized into one or more computer programs, operating system services, or application programs, including mobile applications.Instructions may include an operating system and / or system software; one or more libraries to support multimedia, programming, or other functions; instructions or data protocol stacks to implement TCP / IP, HTTP, or other communication protocols; file format processing instructions to parse or render files encoded in HTML, XML, JPEG, MPEG, or PNG; user interface instructions to render or interpret commands for a graphical user interface (GUI), a command-line interface, or a text-based user interface; application software such as an office suite, Internet access applications, design and manufacturing applications, graphics applications, audio applications, software engineering applications, educational applications, games, or miscellaneous applications.The instructions can implement a web server, a web application server, or a web client. The instructions can be organized as a presentation layer, an application layer, and a data storage layer, such as a relational database system using a query language. structured (SQL) or non-SQL, an object store, a graph-oriented database, a flat file system, or other data storage unit.

[0033] The execution of instructions as described in this section can implement a process in the form of an instance of a computer program that is executed and consists of program code and its ongoing activity. Depending on the operating system (OS), a process may be composed of multiple threads that execute instructions simultaneously. In this context, a computer program is a passive set of instructions, while a process can be the actual execution of those instructions. Several processes can be associated with the same program; for example, opening multiple instances of the same program often means that multiple processes are being executed. Multitasking can be implemented to allow multiple processes to share the processor.While each processor or processor core executes a single task at a time, the computer system can be programmed to implement multitasking, allowing each processor to switch between running tasks without waiting for each task to finish. In one implementation, switchovers can occur when tasks perform input / output operations, when a task indicates that a switchover is possible, or during hardware interrupts. Time-sharing can be implemented to enable fast response times for interactive user applications by rapidly switching contexts to create the appearance of multiple concurrent processes running simultaneously.In one embodiment, for security and reliability reasons, an operating system may prevent direct communication between independent processes, providing strictly mediated and controlled inter-process communication functionality.

[0034] It should be noted that the figures are not to scale.

[0035] Figure 1 schematically represents a particular embodiment of the system 100 that is the subject of the present invention. This predictive maintenance system for aquatic installations 100 may include: - at least one physical / chemical sensor, 110, 115, 116, 117, 181, 182, 183 and 184, interacting with water in at least one aquatic installation and configured to provide a series of at least one detected value representative of a physical / chemical parameter, in which, for example: - at least one physical / chemical sensor, 181, 182, 183 and / or 184, is located in an analysis chamber 180, or in a pipe of a circulation system where water flows, interacting with the water in at least one aquatic installation and configured to provide a series of at least one detected value representative of a physical / chemical parameter and - at least one physical / chemical sensor, 110, 115, 116 and / or 117, is located in a submersible vehicle (ROV) 105 and / or a floating vehicle 106, interacting with water in at least one aquatic installation and configured to provide a series of at least one detected value representative of a physical / chemical parameter, and - at least one processor 120 configured to execute instructions representative of the following steps: - operation of a trained machine learning model, said model being trained to associate, for at least a series of detected values ​​representative of a physical / chemical parameter, at least one aquatic facility operational degradation event with a date of occurrence of the event, and - determination of a sequence of maintenance operations to be carried out on at least one aquatic facility as a function of at least one predicted aquatic facility operational degradation event and the associated date of occurrence of the event.

[0036] The physical and / or chemical sensor, 110, 115, 116, 117, 181, 182, 183 and / or 184, is understood in the broadest sense, which means that any device for detecting physical and / or chemical parameters is included, provided that the output data of such a device is used to assess the physical and / or chemical state of the water in an installation 111 and / or the physical and / or chemical state of the installation 111, and / or the state of the equipment in the aquatic installation.

[0037] Such a physical and / or chemical sensor, 110, 115, 116, 117, 181, 182, 183 and / or 184, is configured to detect a value of a physical and / or chemical parameter at a specific time, allowing a succession of detected values ​​to be associated into a series. Such association can be performed by the physical and / or chemical sensor, 110, 115, 116, 117, 181, 182, 183 and / or 184, or by a computer device receiving a succession of data representative of the values ​​detected by said physical and / or chemical sensor, 110, 115, 116, 117, 181, 182, 183 and / or 184.

[0038] Such a physical and / or chemical sensor, 110, 115, 116, 117, 181, 182, 183 and / or 184, may correspond to, but is not limited to: - a pH sensor, and / or - a total alkalinity sensor, and / or - a conductivity sensor, and / or - a redox potential sensor, and / or - a turbidity sensor, and / or - an optical sensor, and / or - a camera and / or a video camera, and / or - an acoustic and / or sonar sensor, and / or - a temperature sensor, and / or - a flow sensor, and / or - a water movement sensor, and / or - a pressure sensor.

[0039] In particular embodiments, such as that shown in [Fig.1], at least one physical / chemical sensor, 110, 115, 116, 117, 118, 181, 182, 183 and / or 184, is associated with geographic coordinates, the step 215 of determining a sequence being configured to further determine a sequence based on the geographic coordinates of aquatic facilities associated with at least one planned aquatic facility operational degradation event.

[0040] This sensor associated with geographical coordinates can be predefined by a user or determined automatically using a geolocation device, such as a GPS sensor and / or an accelerometer, for example.

[0041] In particular embodiments, such as that shown in [Fig. 1], the system 100 of the present invention comprises at least one physical / chemical sensor which is a device for measuring total aquatic alkalinity 500, comprising: - a pH 505 probe configured to measure the pH at the boundary layer of a body of water, - optionally, a floating reference device 510 near the pH probe, - a probe controller 515, configured to sequentially activate and deactivate, or connect and disconnect, the pH probe, - a pH measurement variation detection device 520, configured to detect a pH measurement variation in a sequence of pH probe measurements, and - a total aquatic alkalinity value determination device 525, configured to determine a total aquatic alkalinity value of the water mass as a function of the detected pH measurement variation.

[0042] The pH probe 505 can be of any type known to a person skilled in the art that is suitable for the particular implementation and intended use of the system 500. Such a pH probe 505 can be of a different nature depending on the context of use of the system 500. For example, in an aquatic installation, the pH probe 505 can include a redox potential sensor 535.

[0043] The purpose of the pH 505 probe is to enable the reproducible measurement of pH in a body of water. Such a pH 505 probe is usually electronic and requires a power supply to operate. This pH 505 probe may also include a digital switch, allowing the selective activation / deactivation of at least some of the core components of the pH 505 probe.

[0044] The pH probe 505 can be mechanically placed at the distal end of a sensor body, as shown in Figures 5 and 6. The purpose of this sensor body is to be inserted into the water mass and, in preferred embodiments, within an analysis chamber 540.

[0045] The floating reference device 510, sometimes called "solution ground" or "liquid junction", can correspond to any electrically conductive electrode or pin configured to normalize the signal detected by the pH probe 505, avoiding electrical noise in the vicinity of the pH probe 505.

[0046] In the example shown in Figures 5 and 6, the floating reference device 510 comprises two electrodes, each located on a different side of a sensor 535 of the probe 505. Such electrodes may be diametrically opposed, with the sensor 535 acting as the center of a circle in which the two electrodes are located on the periphery of said circle, for example. Such electrodes and the sensor 535 may be geometrically aligned.

[0047] In particular embodiments, such as that shown in [Fig. 5], the pH probe 505 comprises: - optionally, the floating reference device 510, - a microporous glass bulb membrane 530, and - a redox potential sensor 535.

[0048] The pH measurement is based on the relationship between the H+ ion concentration of the water being tested and the electrochemical potential difference established in the lead-free glass bulb membrane of the probe. This lead-free bulb is specifically designed to be selective for H+ ion concentration.

[0049] In general, the pH probe 505 consists of a simple electronic amplifier and a combined electrode, consisting of two electrodes: one whose potential is known and constant and the other whose potential varies with pH.

[0050] Once the probe 505 comes into contact with the water, H+ ions are exchanged on the glass bulb, creating an electrochemical potential across the bulb. The electronic amplifier detects the electrical potential difference between the two electrodes generated during the measurement and converts the potential difference into pH units.

[0051] The pH value is determined by correlation because the potential difference between the two electrodes evolves proportionally to the pH according to the Nemst equation.

[0052] The probe controller 515 is, for example, an electronic circuit configured to electrically or electronically turn on and off, or connect and disconnect, the pH probe 505 or the sensor of said pH probe 505. Such activation / deactivation or connection / disconnection can be effected by switching off and restoring the power supply to the pH probe 505 or the sensor or by issuing an activation / deactivation or connection / disconnection command to said pH probe 505 or said sensor or relay.

[0053] The terms "activate and deactivate" refer to any hardware or software level activation / deactivation and / or connection / disconnection of the pH 505 probe.

[0054] The probe controller 515 can itself be activated according to a command issued by a computer device, located on site and mechanically connected to the pH probe 505 and / or the probe controller 515 or located remotely and connected to the probe controller 515 by means of a data connection.

[0055] The probe controller 515 may include, for example, computer software running on a computer device, said computer software triggering the activation / deactivation or connection / disconnection of the pH probe 505. Such computer software may correspond, for example, to specific firmware or a particular driver. Such computer software may be updated remotely, and such an update may be automatically installed in the system 500.

[0056] The probe controller 515 can be configured to periodically activate or connect the pH probe 505. The pH probe can be physically activated or connected, for example, every 60 seconds. Such activation or physical connection can be contingent, for example, on the activation of a water displacement pump. The measurement speed can be variable depending on a configured mode. The measurement duration can depend on the stability of the water, so that the pH measurement continues until the measured pH is sufficiently stable.

[0057] Such activation / deactivation can be performed by an electronic relay.

[0058] The pH measurement variation detection device 520 is, for example, an electronic device associated with the pH probe 505, configured to record a succession of pH values ​​measured by the pH probe 505 and to calculate, from said succession, a measurement variation value. Such a measurement variation value can be calculated by subtracting a recent value from an older value.

[0059] The measured variation can be performed on immediately subsequent measured pH values ​​or sampled according to a particular sampling rule. Such a variation can also be performed on a cumulative set of measured pH values.

[0060] For example, the pH measurement variation detection device 520 can be configured to subtract the average pH value measured during a more recent specific period of time from the average pH value measured during an older specific period of time.

[0061] For example, the pH 520 measurement variation detection device can be configured to calculate a mathematical function corresponding to a succession of Data points link the measured pH to the measurement time since an initial measurement. One such example is shown in [Fig. 7]. In other examples, the pH 520 measurement variation detection device can be configured to store, in memory, a sequence of data points linking the measured pH to the measurement time since an initial measurement.

[0062] The system 500 may further include a timestamping means, configured to associate a measurement time with a pH value detected by the pH probe 505.

[0063] Repeatedly measuring the pH in the same water sample induces variations in the pH measurement, the magnitude of these variations depending on the total alkalinity of the water. Such a pH measurement variation detection device 520 can also be computer software running on a computer.

[0064] The pH measurement variation detection device 520 can operate remotely from the pH probe 505. In such a case, the system 500 may further include a communication means 565 for transmitting data from the pH probe 505 to the pH measurement variation detection device 520. In such a case, the pH measurement variation detection device 520 may correspond to a computer program executed by a computer server, accessible on the cloud, via a data network such as the Internet, for example.

[0065] The device for determining the value of total aquatic alkalinity 525 is, for example, an electronic device associated with the pH measurement variation detection device 520, configured to associate a total alkalinity value with the measured variation.

[0066] For example, the total alkalinity value determination device 525 can be configured to calculate the derivative of a mathematical function corresponding to a succession of data points relating the measured pH to the measurement time since an initial measurement. Such an example is shown in [Fig. 7].

[0067] The total alkalinity value determination device 525 can be configured to associate, with specific derivatives or ranges of said derivatives, a specific total alkalinity value or a range of total alkalinity values.

[0068] For example, in [Fig.7]: - a first series of 805 pH measurements (Y-axis), at specific times (X-axis), measured in minutes, from an initial measurement, for a total alkalinity value of 220 mg / l, - a second series of 810 pH measurements (Y-axis), at specific times (X-axis), measured in minutes, from an initial measurement, for a total alkalinity value of 125 mg / l, and - a third series of 815 pH measurements (Y axis), at specific times (X axis), measured in minutes, from an initial measurement, for a total alkalinity value of 19 mg / l.

[0069] Obtaining such series relating pH to alkalinity can be achieved by empirically measuring, for different total alkalinity values ​​and a determined activation / connection frequency for the pH sensor, the pH values ​​in the boundary layer of a water body and storing these series in memory. The number of these tests to be performed is limited in terms of scope, given the limited number of alkalinity values.

[0070] Such a total alkalinity value can be a mathematical function of the measured variation. Such a mathematical function can be realized by determining a regression function based on the captured pH series, or values ​​derived from these series, as well as the operational parameters associated with the capture.

[0071] Such derived values ​​can be, for example, any type of means or parameters of derived functions.

[0072] For example, the following mathematical formula can be used (with initial parameter values: pH = 7.4; water temperature = 20 °C; redox = 700 mV; flow rate = 0 m³ / h): Ouch = - 0.000 l(MOYi-MOY2) + 0.1468

[0073] Where: - Ale denotes the total alkalinity value, - MOYj denotes the average pH values ​​measured from 20 seconds to 80 seconds after the initial measurement. - MOY2 refers to the average pH values ​​measured 300 seconds to 360 seconds after the initial measurement, Such a function can be approximated &Alc = ( MOYf - MOY. ).

[0074] From such a function, the following lookup table can be obtained: Total alkalinity value (AVERAGE) - AVERAGE 2 10 0.1368 20 0.1268 30 0.1168 40 0.1068 50 0.0968 60 0.0868 70 0.0768 80 0.0668 90 0.0568 100 0.0468 110 0.0368 120 0.0268 130 0.0168 140 0.0068 150 -0.0032 160 -0.0132 170 -0.0232 180 -0.0332 190 -0.0432 200 -0.0532

[0075] Such a total alkalinity value can be determined based on the measured variation and a predefined threshold value, representative of a particular total alkalinity value.

[0076] Such a device for determining the value of total aquatic alkalinity 525 can also correspond to computer software running on a computer device.

[0077] The device for determining the value of total aquatic alkalinity 525 can operate remotely from the pH probe 505 and / or the pH measurement variation detection device 520. In such a case, the system 500 may further include a communication means 565 for transmitting data from the pH measurement variation detection device 520 to the device for determining the value of total aquatic alkalinity 525. In such a case, the device for determining the value of total aquatic alkalinity 525 may correspond to a computer program executed by a computer server, accessible on the cloud, via a data network such as the Internet, for example.

[0078] In particular embodiments, the pH probe controller 515 is configured to sequentially activate and deactivate, or connect and disconnect, the pH probe 505 in a body of water without flow. Such a state can be achieved by stopping a pumping system introducing water into the body of water. In particular variants, the pH probe 505 can be activated after detection of a absence of flow (for example, due to a flow sensor). In particular, a chamber containing the pH 505 probe may have valves that can be closed before the activation / deactivation or connection / disconnection sequence operation of the pH 505 probe.

[0079] The expression "non-flowing water mass" refers to a water mass with limited water flow. In such a water mass, water can circulate, but only a limited amount of new water can enter.

[0080] In particular embodiments, the pH probe 505 is configured to be positioned in a small volume of water. This small volume may correspond, for example, to 1 to 2 milliliters.

[0081] The expression "small volume water mass" refers to a water mass in which the chemical reaction taking place during a deactivation / activation, or connection / disconnection, interval of the pH 505 probe has a significant impact on the pH measurement so as to exhibit a variation between two successive pH measurements by the pH 505 probe.

[0082] In particular embodiments, the system 500 of the present invention comprises an analysis chamber 540, including an opening 545, a main volume 550 connected to the opening 545 and a recess 555 in the main volume 550, the pH probe 505 being in contact with the water in the recess 555.

[0083] The analysis chamber 540 may include a sensor housing 541 delimiting an internal volume into which the pH probe 505 or a sensor body associated with said pH probe 505 may be inserted.

[0084] The analysis chamber 540 is preferably configured to limit the flow of water and the volume of water near the pH probe 505. Such a configuration can be achieved by selecting dimensions that limit the amount of water entering the analysis chamber 540.

[0085] The analysis chamber 540 has an opening 545, of arbitrary dimensions, which allows the passage of water from the water mass to the vicinity of the pH probe 505.

[0086] The analysis chamber 540 has a main volume 550, defined for example by the internal dimensions of the sensor housing 541.

[0087] The analysis chamber 540 includes a recess 555, defined by a subset of the internal dimensions of the sensor housing 541. In particular embodiments, the recess 555 is formed by crenellated sensor body extensions 556 associated with the pH probe 505, said crenellated sensor body extensions 556 limiting the movement of water in the vicinity of the pH probe 505.

[0088] There are many possible configurations of the analysis chamber 540. Such configurations preferably limit the amount of water near the pH probe 505 and / or limit the movement of water near the pH probe 505.

[0089] In particular embodiments, the system 500 of the present invention comprises a remote computer device 560 including the device for determining the value of total aquatic alkalinity 525 and a means of communication 565 between the device for detecting variation in pH measurement 520 and the device for determining the value of total aquatic alkalinity 525.

[0090] Such a remote computing device 560 can correspond, for example, to a computer server hosted remotely and accessible via a data network, such as the Internet for example.

[0091] In particular embodiments, the device for determining the value of total aquatic alkalinity 525 uses an algorithm and / or a trained machine learning model to associate a value of total aquatic alkalinity with a variation in the measured pH.

[0092] In particular embodiments, the pH probe 505 is configured to measure the pH of the water mass in an aquatic installation.

[0093] In particular embodiments, the pH probe 505 is configured to measure the pH of the mass of water in a pipe.

[0094] In particular embodiments, such as that shown in [Fig.1], the system 100 of the present invention comprises a submersible and / or floating vehicle 105, 106, including at least one said physical / chemical sensor, 110, 115, 116 and / or 117, configured to provide a measurement of a local physical / chemical parameter in the vicinity of the submersible and / or floating vehicle.

[0095] The submersible and / or floating vehicle 105 and / or 106 may correspond, for example, to any manually, remotely and / or automatically steerable vehicle adapted to the particular use case.

[0096] The vehicle 105 may correspond to a remotely or autonomously steerable underwater vehicle, for example, as shown in [Fig.3].

[0097] The vehicle 106 can also correspond to a floating device, as shown in [Fig.4].

[0098] In particular embodiments, such as that shown in [Fig.1], the system 100 comprises both a submersible vehicle (ROV) 105 and a floating vehicle 106.

[0099] In particular variants, at least one submersible and / or floating vehicle 105 and / or 106 includes a solar panel 305 configured to power an autonomous power source (not shown) and / or to charge the on-board batteries (not shown).

[0100] In particular variants, at least one submersible and / or floating vehicle 105 and / or 106 includes an induction current collector configured to supply a self-contained power source (not shown).

[0101] In particular variants, at least one submersible and / or floating vehicle 105 and / or 106 has a power input configured to be connected to a charging cable to power a self-contained power source (not shown).

[0102] In particular embodiments, at least one submersible and / or floating vehicle 105 and / or 106 includes a propulsion system 310, such as a motor associated with a boat propeller. Such a propulsion system 310 enables the vehicle 105 and / or 106 to move in the water of the installation 111. This propulsion system 310 may include rear propellers 320, configured to generate forward, rearward, or yaw movements, and a front propeller 315, configured to generate upward or downward movements.

[0103] Such a submersible and / or floating vehicle 105 and / or 106 may further include a means for acquiring relative positioning coordinates, configured to locate, in a three-dimensional space representative of the aquatic installation 111, the submersible vehicle 105 and / or 106 and to provide the corresponding coordinates of the submersible and / or floating vehicle 105 and / or 106.

[0104] Such a means of acquiring relative positioning coordinates is, for example, an acoustic and / or sonar sensor configured to provide distance values ​​from the edges of the installation 111. The distance values ​​make it possible to determine the shape of the installation 111. Once the shape of the installation 111 is known, such distance values ​​make it possible to determine the positioning of the submersible and / or floating vehicle 105 and / or 106 within said installation 111.

[0105] In another variant, the means for acquiring relative positioning coordinates is, for example, a mechanical sensor used in coordination with a propulsion system 310 to map the shape of the installation 111 by detecting collisions of the submersible and / or floating vehicle 105 and / or 106 with the edges of this installation 111.

[0106] Once the shape of the installation 111 is known, information from the original parameters of the propulsion system 310 can be used to locate the submersible and / or floating vehicle 105 and / or 106. For example, a duration of use of the propulsion system 310, associated with a propulsion power, can be used in a calculation to determine a distance of the submersible and / or floating vehicle 105 and / or 106, relative to the last known location.

[0107] The data resulting from the physical and / or chemical detection means 110 and the relative positioning coordinate acquisition means can be aggregated to form a time-stamped physical and / or chemical value of the detected water. These data can also be associated with environmental context values, such as water pressure or capture time, for example.

[0108] In particular variants, the submersible and / or floating vehicle 105 and / or 106 includes a means for aggregating local physical and / or chemical state information of an aquatic installation.

[0109] The means for aggregating local physical and / or chemical state information of an aquatic installation is, for example, computer software running on a computer device. This computer device is configured to associate, in a memory, the data resulting from the relative positioning coordinate acquisition means, the physical and / or chemical detection means 110, and a time-stamping means.

[0110] Such an association can be achieved by concatenating said data into a single data stream or data frame or by creating a link between said data if this data is stored in separate database tables, for example.

[0111] The timestamping means may correspond, for example, to any electronic clock used by a computer device. Such a timestamping means may be integrated into the submersible and / or floating vehicle 105 and / or 106 or be located remotely from said submersible and / or floating vehicle 105 and / or 106. By located remotely, it is understood that the timestamping means is connected to the submersible and / or floating vehicle 105 and / or 106 by a means of communication, such as a point-to-point link or a communication network link, such as the Internet for example.

[0112] The submersible and / or floating vehicle 105 and / or 106 may further include an optical sensor 115, configured to provide a graphical representation of the water and / or aquatic installation, said representation being used during the operating stage of the trained machine learning model.

[0113] Such an optical sensor 115 corresponds, for example, to a camera or video camera configured to capture images of the installation 111 and / or the water in the installation 111. In particular embodiments, this camera and / or video camera can be used to capture images and / or videos of the floor and walls of a water tank to detect stains and determine their origin and / or nature based on the color, location, and shape of said stains. In particular embodiments, this camera and / or video camera can be used to determine the transparency and / or turbidity of the water by analyzing the resolution and / or acquisition rendering of a specific target point location and / or target device at a specific location in the pool.In particular embodiments, this target point and / or target device could be the inductive load plate, and / or the walls and / or the floor of the installation, and / or a dedicated device placed in a defined location.

[0114] In particular embodiments, such as that shown in [Fig. 1], the optical sensor 115 includes an infrared sensor 116. In particular embodiments, the infrared sensor 116 can acquire thermal images, enabling the determination of changes and / or differences in water temperature within the installation. In particular embodiments, said changes and / or differences in temperature can be recorded and associated with the location to create a temperature map along three axes as a function of measurement time.In particular embodiments, this mapping can be used to adjust the homogeneity of the water temperature in the installation by adjusting, for example, the flow rate of the filtration pump and / or the operating time of the filtration and / or the operating time of the heat pump and / or the temperature setpoint of the heat pump and / or the filter cleaning process, increasing or decreasing their values ​​to achieve the target temperature homogeneity in the installation.

[0115] In particular embodiments, such as that shown in [Fig. 1], the submersible and / or floating vehicle 105 and / or 106 includes an acoustic and / or sonar sensor 117.

[0116] Based on the sound changes perceived by the acoustic and / or sonar sensor, notifications and / or alerts can be issued and / or the operating setpoint of the equipment can be adjusted automatically.

[0117] For example, a pump emits a specific sound (vibration signature) at the start of operation. These vibrations follow the flow of water in the system 111. Therefore, the use of an acoustic and / or sonar sensor allows for the measurement and analysis of these vibrations. Any change in this signature results from an interaction and / or a problem that has occurred between the pump and the system 111. Such an interaction could correspond to a pump failure, a pump overload, pump cavitation, the presence of an object / contaminant in the pipe, a leak, or product injection. By measuring the difference between the sound under normal conditions and the currently measured sound, a diagnosis can be performed, and / or notifications and / or alerts can be issued, and / or the operating setpoint of the equipment can be automatically adjusted.This difference may also be related to other types of data collected.

[0118] Any sound that may occur in the installation 111 can be linked to a type, or category, of event. The determination of this category can be obtained using a trained machine learning classifier model. Such a trained machine learning classifier model can be obtained by introducing, into a machine learning classifier device, a sample comprising sounds and their associated events. Such a classifier model Trained machine learning can be obtained by introducing, into a machine learning classifier device, a sample comprising the sound in the facilities in the absence of an event (or anomaly), the sound in the facilities after an event, and the associated events.

[0119] Such a sound may correspond to a bather diving, an object entering the water installation, the presence of an object in the installation's pipe, raindrops, bathers swimming or playing, a release of air below the water's surface, overflow problems, full skimmer baskets, a different flow rate or an opening / closing of the cover, or the presence of an automatic cleaner in operation.

[0120] This audible alarm system can be used to detect a bather in distress and / or drowning.

[0121] In particular embodiments, such as that shown in [Fig.1], the system 100 of the present invention includes an external parameter sensor 118, the trained model being configured to associate, for at least one series of detected values ​​representative of a physical / chemical parameter and at least one series of detected external parameters, at least one operational degradation event of an aquatic installation associated with a date of occurrence of the event.

[0122] Such an external parameter sensor 118 may correspond to any physical / chemical sensor, such as a camera and / or video camera taking an image and / or filming the installation 111, or a digital sensor, such as a connector to a weather forecasting API configured to provide data representative of current or future weather conditions in the vicinity of the installation 111.

[0123] Such an external parameter sensor 118 can be configured to detect values ​​representative of weather conditions, and / or air pollution, and / or a certain number of bathers in the aquatic facility, and / or air temperature, and / or water temperature, and / or motion detection, and / or facial recognition, and / or color change detection, and / or stain and / or dirt detection in the facility, and / or size detection, and / or shape acquisition and / or detection, and / or contrast detection within the water of the facility, for example.

[0124] The data representing the values ​​detected by at least one sensor, 110, 115, 116, 117, 118, 181, 182, 183, 184 and / or 500, are transmitted to a computer system 900, such as that shown in [Fig.9].

[0125] This computer system 900 includes at least one processor 120 configured to execute instructions, which may correspond to computer software, representative of at least the following steps, as shown in [Fig.8]: - operation 210 of a trained machine learning model, said model being trained to associate, for at least one series of detected values ​​representative of a physical / chemical parameter, at least one operational degradation event of an aquatic installation with a date of occurrence of the event, and - determination 215 of a sequence of maintenance operations to be carried out on at least one aquatic installation based on at least one planned operational degradation event of aquatic installation and the associated date of occurrence of the event.

[0126] During step 210 of operation, a trained machine learning model obtained during a (not shown) training step of said machine learning model is applied to the data generated by the operation of at least one sensor 110, 115, 116, 117, 118, 181, 182, 183, 184 and / or 500.

[0127] The type of machine learning device used to obtain the trained machine learning model can be any type suitable for the nature and format of the data generated by the operation of at least one sensor 110, 115, 116, 117, 118, 181, 182, 183, 184 and / or 500.

[0128] Such a machine learning device may use at least one of the following types of machine learning processes: - supervised learning, in which the machine learning model is trained to predict an output based on an input, using a set of examples, - unsupervised learning, in which the machine learning model is trained to identify patterns in the data without any assistance, - semi-supervised learning, in which the machine learning model is trained on both labeled and unlabeled data, - reinforcement learning, in which the machine learning model is trained based on the rewards and penalties it receives for its actions, and / or - deep learning, in which the machine learning model is trained using artificial neural networks to learn and make decisions.

[0129] Such a machine learning device may use at least one of the following types of deep learning processes: - Convolutional neural networks (CNNs), often used for image and video processing tasks, such as object recognition, image classification, and segmentation, - recurrent neural networks (RNNs), often used for sequential data processing, such as natural language processing (NLP), speech recognition and time series analysis, and / or - attention models, often used for machine learning models that need to focus selectively on different parts of the input.

[0130] Such a machine learning device can use a set of neural networks, for example.

[0131] The output of operating step 210 is a list of at least one facility operational degradation event, i.e. an event requiring maintenance and preferably proactive maintenance, and the dates of occurrence of said event.

[0132] Such an operational degradation event of an installation may correspond to, but is not limited to: - a low, critically low or empty level of a consumable used in a water treatment circuit associated with installation 111, and / or - a malfunction or failure of a device, said device belonging to a water treatment circuit associated with installation 111, or interacting with said installation 111, and / or - a state of the water in installation 111, said state being representative of a level of acidity or alkalinity, or of a behavior of the water (scale-forming or aggressive) for example, and / or - a low, high, or inappropriate disinfection rate and / or a high or inappropriate level of disinfection residues (such as combined chlorine when active chlorine is used as the primary disinfectant) in the facility 111, said rate being measured with dedicated sensors, with values ​​that are lower or higher than the user's setpoint and / or the values ​​tolerated by local regulations and / or by disinfection algorithms that continuously adjust the ideal values ​​based on the uses of the aquatic facility and real-time requirements, and / or - a low, high, or inappropriate value of a chemical parameter, such as total alkalinity and / or pH and / or cyanuric acid content, and / or salt content, and / or phosphate compound levels, and / or sulfate levels, and / or nitrate levels, and / or nitrite levels, and / or chlorate levels, and / or - low, high, or inappropriate pressure measured in the filter and / or in the pipes and / or in the filtration pump, and / or - a low, high, or inappropriate flow measured in the filter and / or in the pipes and / or in the filtration pump, and / or - leak detection, and / or - excessive consumption of filling water, and / or - a low or high water level in the installation, and / or - excessive energy consumption, and / or - high turbidity in the aquatic installation, and / or - a high presence of particles in the aquatic installation, and / or - detection of stains and / or dirt, and / or - a high number of metallic compounds, and / or - the number of users and / or bathers in the aquatic facility, and / or - a predicted or unforeseen climate change that could occur during the coming period, and / or - the impact of short- and long-term climate change on the ability of aquatic facilities to operate correctly and according to control parameters, and / or - a change in the color of the water, and / or - a detected presence of an unauthorized object and / or animal, and / or - a failure to increase temperature or a non-uniform temperature in the water installation.

[0133] The exit date of the operating step 210 can be an absolute date (“March 3” or a relative date (“in one week”, “within 3 days”, “within 24 hours”).

[0134] In more advanced embodiments, the operating step 210 is configured to associate other parameters with a prediction of the occurrence of an operational degradation event in the facility. These other parameters may correspond, for example, to a criticality level of the event or the operating time to resolve it.

[0135] In more advanced embodiments, the operating step 210 is configured to associate several dates with a predicted occurrence of an operational degradation event in the facility. These dates correspond, for example, to changes in the criticality of the event, such as, for example, a consumable going from a low level to a critically low level or to an empty level.

[0136] Step 215 of determining a sequence of maintenance operations to be performed corresponds, for example, to a resource allocation algorithm. Such a resource allocation algorithm can be configured to plan, that is, to organize in time, a sequence of maintenance operations.

[0137] Such an organization can be based solely on the planned dates of occurrence of events obtained during step 210 of operation.

[0138] In more advanced embodiments, such an organization can be based on secondary criteria, such as operator-event compatibility, Product availability, event locations, and operating costs are all factors to consider. Examples of such implementations are disclosed below.

[0139] In particular embodiments, at least one processor 120 is configured to execute instructions representative of a step 225 of assignment, for at least one event planned in a sequence of maintenance operations, of an operator identifier according to the operator parameters associated with the operator identifier.

[0140] In simple embodiments, during the assignment step 225, each event in the event sequence is associated with an event identifier and each operator is associated with an operator identifier.

[0141] An event identifier corresponds, for example, to a bijective code (such as an alphanumeric or binary code) that corresponds to the numerical representation of an event. An event identifier may be associated with additional information, such as the date of the event, the location of the event, the type of event, and the maintenance status of the event, for example.

[0142] An operator identifier corresponds, for example, to a bijective code (such as an alphanumeric or binary code) that corresponds to the numerical representation of an operator. An operator identifier may be associated with additional information, such as the name of the operator, a type of event that the operator can handle, an operator location, and an operator state, for example.

[0143] This operator assignment can be automatic (entirely carried out by software), semi-automatic (based on suggestions from software validated or modified by a user) or manual (defined by a user on a graphical user interface for example).

[0144] The assignment can be materialized by the creation of a link (such as a key in a database table), in memory, between an event identifier and an operator identifier.

[0145] Such an assignment may follow assignment rules, such as, for example: - an operator identifier cannot be associated with an event identifier if the operator identifier is associated with another event identifier at the same date and time or during an interval surrounding the associated event that would prevent the operator from being fully available for the second event, and / or - An operator identifier cannot be associated with an event identifier if the event identifier is associated with a date that is below a specified threshold of the date of another event identifier already assigned to the operator that exceeds a threshold value determined in relation to the location of said event already assigned.

[0146] In a multi-installation and multi-operator context, this means that a user and / or software can assign operators to maintain installations on a many-to-many basis.

[0147] In particular embodiments, at least two operator identifiers are assigned during the assignment step 225, at least one processor 120 being configured to execute instructions representative of the following steps: - transmission 230, to a third-party computer system associated with a user identifier, of at least two of said operator identifiers, and - reception 235, from a third-party computer system associated with the user identifier, of a selection of at least one of the at least two of said operator identifiers.

[0148] The transmission 230 and reception 235 steps can be carried out using any means of communication, or I / O subsystem as shown in [Fig.9].

[0149] For example, during transmission step 230, a digital message comprising at least two of said operator identifiers assigned to a planned event, together with the event identifier, is sent to a computer system belonging to, or associated with, a user identifier.

[0150] A user identifier corresponds, for example, to a bijective code (such as an alphanumeric or binary code) that represents the numerical identity of a user. A user identifier is usually associated with an owner of an aquatic facility or with an aquatic facility manager responsible for several aquatic facilities.

[0151] The third-party IT system corresponds, for example, to a computer or smartphone belonging to the user. The message may also correspond to a notification, for example by email, inviting the user to log in to facility management software with a graphical user interface. Such facility management software may provide several functionalities: - monitoring the status of aquatic installations, and / or - predicting maintenance events for aquatic installations, and / or - assigning operators for maintenance events, and / or - purchasing and assigning products for maintenance events, and / or - self-help resources to independently perform maintenance on the water installation.

[0152] Using the third-party computer system, a user selects at least one operator identifier to manage the aquatic facility operational degradation event.

[0153] For example, during the reception step 235, user input is recorded on a graphical user interface, said input being representative of a selection of at least one operator identifier. Such input can be made, for example, on a smartphone or a computer, triggering a selection of operator identifiers by the computer system 900.

[0154] In particular embodiments, at least one expected event is associated with an event type identifier, at least one operator parameter representing operator-event type identifier compatibility.

[0155] Such an event type identifier corresponds, for example, to a bijective code (such as an alphanumeric or binary code) that corresponds to the numerical representation of a degradation event type. Examples of such degradation event types are mentioned above. Other such examples might correspond, for example, to: - hydraulic circuit events, and / or - Consumable refill events, and / or - Installation maintenance events, and / or - Electrical repair maintenance events, and / or - Filter-related maintenance events, and / or - maintenance events related to the pump, and / or - equipment maintenance events at the facility, and / or - maintenance events for sensors of the installation equipment.

[0156] Each planned operational degradation event of an aquatic facility can be associated with at least one event type identifier, and each operator can be associated with at least one event type identifier. This operator-event type association can be performed in facility management software to which operators can log in, where they can configure their account and the event type associations. These associations can also be made by facility managers or pool owners by registering operators and associating event types with said operators.

[0157] In particular embodiments, at least one processor 120 is configured to execute instructions representative of a step 240 of identifying at least one product identifier representative of a product to be used during the determined sequence of maintenance operations.

[0158] A product identifier corresponds, for example, to a bijective code (such as an alphanumeric or binary code) that represents the numerical value of a product to be used in the maintenance to be performed. A product identifier may correspond to a consumable or to any piece of aquatic installation equipment, for example.

[0159] Step 240 of identification can be carried out by reading, from memory, product identifiers proactively associated with operational degradation event identifiers of aquatic installation. Such association can be performed automatically, semi-automatically, or manually by a user.

[0160] Such identified products may be communicated to a user of the system, usually a user associated with the aquatic installation 111 being maintained.

[0161] In particular embodiments, at least two product identifiers are identified during the identification step 240, at least one processor 120 being configured to execute instructions representative of the following steps: - transmission 245, to a third-party computer system associated with a user identifier, of at least two of said product identifiers, and - reception 250, from a third-party computer system associated with the user identifier, of a selection of at least one of the at least two of said product identifiers.

[0162] The transmission step 245 and the reception step 250 can operate in the same way as the transmission step 230 of at least two operator identifiers and the reception step 235 of at least one operator identifier. Instead of selecting an operator, the user selects a product.

[0163] In particular embodiments, at least one processor 120 is configured to execute instructions representative of an estimation step 255 of a product impact index, representative of the ability of a product to resolve an operational degradation event of an aquatic facility, said index being associated with at least one product identifier identified and transmitted during the transmission step.

[0164] Such an estimation step 255 can be carried out, for example, by retrieving a product impact index from a product-event identifier matrix storing representative values ​​of the impact of a particular product for a particular type of event. This product impact index is representative of the ability of a particular product to contribute qualitatively to the resolution of a particular event.

[0165] In particular embodiments, at least one processor 120 is configured to execute instructions representative of an emission step 260, to a third-party computer system associated with at least one selected product identifier, of a message representative of a purchase order for at least one product associated with at least one selected product identifier.

[0166] Such an emission step 260 can be carried out using an I / O subsystem or a communication means of a computer system 900 as shown in [Fig.9].

[0167] The message sent may also include information representative of a shipping location for the purchased product.

[0168] Figure 2 schematically represents a particular sequence of steps in the process 200 that is the subject of the present invention. This predictive maintenance process for an aquatic installation 200 comprises: - at least one step 205 of operation of a physical / chemical sensor interacting with water in at least one aquatic facility to provide a series of at least one detected value representative of a physical / chemical parameter, - one step 210 of operation of a trained machine learning model, said model being trained to associate, for at least one series of detected values ​​representative of a physical / chemical parameter, at least one operational degradation event of an aquatic facility with a date of occurrence of the event, and - a step 215 of determining a sequence of maintenance operations to be carried out on at least one aquatic installation based on at least one planned operational degradation event of aquatic installation and the associated date of occurrence of the event.

[0169] Particular embodiments of the operating steps of the physical / chemical sensor 205, of the operation 210 of a trained machine learning model and of determination 215 are disclosed above.

[0170] Figure 9 represents a functional diagram illustrating an example of a computer system 900 with which an embodiment can be implemented. In the example in Figure 9, a computer system 905 and instructions for implementing the disclosed technologies in hardware, software, or a combination of hardware and software are represented schematically, for example, in the form of boxes and circles, at the same level of detail commonly used by the ordinary person skilled in the art to which this disclosure relates for communicating about implementations of computer architecture and computer systems.

[0171] The computer system 905 includes an input / output (I / O) subsystem 920 which may include a bus and / or one or more other communication mechanisms for the communication of information and / or instructions between the system components Computer 905 on electronic signal paths. The I / O subsystem 920 may include an I / O controller, a memory controller, and at least one I / O port. Electronic signal paths are represented schematically on the drawings, for example, as lines, unidirectional arrows, or bidirectional arrows.

[0172] At least one hardware processor 910 is coupled to the I / O subsystem 920 for information and instruction processing. The hardware processor 910 may include, for example, a general-purpose microprocessor or microcontroller and / or a special-purpose microprocessor such as an integrated system or a graphics processing unit (GPU) or a digital signal processor or an ARM processor. The processor 910 may include an integrated arithmetic logic unit (ALU) or may be coupled to a separate ALU.

[0173] The computer system 905 includes one or more memory units 925, such as main memory, which is coupled to the I / O subsystem 920 for the digital electronic storage of data and instructions to be executed by the processor 910. The memory 925 may include volatile memory such as various forms of random access memory (RAM) or other dynamic storage device. The memory 925 may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processor 910. Such instructions, when stored on non-transient storage media that are readable by the computer and accessible to the processor 910, can transform the computer system 905 into a special-purpose machine that is customized to perform the operations specified in the instructions.

[0174] The computer system 905 further includes non-volatile memory such as read-only memory (ROM) 930 or another static storage device coupled to the I / O subsystem 920 for storing information and instructions for the processor 910. The ROM 930 may include various forms of programmable ROM (PROM) such as erasable PROM (EPROM) or electrically erasable PROM (EEPROM). A persistent storage unit 915 may include various forms of non-volatile RAM (NVRAM), such as FLASH memory, or a solid-state storage unit, a magnetic disk or an optical disk such as CD-ROM or DVD-ROM, and may be coupled to the I / O subsystem 920 for storing information and instructions.The 915 storage unit is an example of computer-readable non-transient media that can be used to store instructions and data which, when executed by the 910 processor, result in the realization of computer-implemented processes to carry out the techniques herein.

[0175] The instructions in memory 925, ROM 930, or storage unit 915 may comprise one or more sets of instructions organized into modules, processes, objects, functions, routines, or calls. The instructions may be organized into one or more computer programs, operating system services, or application programs, including mobile applications.Instructions may include an operating system and / or system software; one or more libraries to support multimedia, programming, or other functions; instructions or data protocol stacks to implement TCP / IP, HTTP, or other communication protocols; file format processing instructions to parse or render files encoded in HTML, XML, JPEG, MPEG, or PNG; user interface instructions to render or interpret commands for a graphical user interface (GUI), a command-line interface, or a text-based user interface; application software such as an office suite, Internet access applications, design and manufacturing applications, graphics applications, audio applications, software engineering applications, educational applications, games, or miscellaneous applications.The instructions can implement a web server, a web application server, or a web client. The instructions can be organized as a presentation layer, an application layer, and a data storage layer, such as a relational database system using a structured query language (SQL) or without SQL, an object store, a graph database, a flat file system, or another data storage unit.

[0176] The computer system 905 can be coupled via the I / O subsystem 920 to at least one output device 935. In one embodiment, the output device 935 is a digital computer display or a human-machine interface. Examples of a display that can be used in various embodiments include a touchscreen display, a light-emitting diode (LED) display, a liquid crystal display (LCD), or an electronic paper display. The computer system 905 can include one or more other types of output devices 935, either as an alternative to or in addition to a display device. Other output devices 935 include, for example, printers, ticket printers, plotters, projectors, sound or video cards, loudspeakers, buzzers or piezoelectric devices or other audible devices, LED or LCD lamps or indicators, haptic devices, actuators, or servos.

[0177] At least one input device 940 is coupled to the I / O subsystem 920 for communicating signals, data, command selections, or gestures to the processor 910. Examples of input devices 940 include touchscreens, microphones, digital fixed and video cameras, alphanumeric and other keys, numeric keypads, keyboards, graphics tablets, image scanners, joysticks, clocks, switches, buttons, dials, slides.

[0178] Another type of input device is a control device 945, which can perform cursor control or other automated control functions such as navigating a graphical user interface on a display screen, either as an alternative to or in addition to the input functions. The control device 945 can be a touchpad, a mouse, a trackball, or cursor direction keys to communicate direction information and control selections to the processor 910 and to control cursor movement on the display 935. The input device can have at least two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), which allows the device to specify positions in a plane.Another type of input device is a wired, wireless, or optical control device such as a joystick, pen reader, console, steering wheel, pedal, gear shifter, or other type of control device. A 940 input device may include a combination of several different input devices, such as a video camera and a depth sensor.

[0179] In another embodiment, the computer system 905 may include an Internet of Things (IoT) device in which one or more of the output device 935, input device 940, and control device 945 are omitted. Or, in such an embodiment, the input device 940 may include one or more cameras, motion detectors, thermometers, microphones, seismic detectors, other sensors or detectors, measuring devices, or encoders, and the output device 935 may include a special display such as a one-line LED or LCD screen, one or more indicators, a display panel, a counter, a valve, a solenoid valve, an actuator, or a servo.

[0180] The computer system 905 can implement the techniques described herein by using custom hardwired logic, at least one ASIC or FPGA, firmware, and / or program instructions or logic which, when loaded and used or executed in combination with the computer system, causes the computer system to operate or program as a special-purpose machine. In one embodiment, the techniques described herein are performed by the computer system 905 in response to the execution by the processor 910 of at least one sequence of at least one instruction contained in main memory 925. Such instructions may be read from main memory 925 from another storage medium, such as the storage unit 915. The execution of the sequences The instructions contained in main memory 925 cause the processor 910 to perform the process steps described here. In alternative embodiments, hardwired circuits may be used instead of, or in combination with, software instructions.

[0181] The term "storage medium" as used herein means any non-transient medium that stores data and / or instructions that cause a machine to operate in a specific manner. Such storage media may include non-volatile and / or volatile media. Non-volatile media include, for example, optical or magnetic disks, such as the 915 storage unit. Volatile media include dynamic memory, such as the 925 memory. Common forms of storage media include, for example, a hard disk drive, an integrated circuit disk, a USB flash drive, a magnetic data storage medium, any optical or physical data storage medium, a memory chip, or the like.

[0182] The storage medium is separate but can be used in conjunction with a transmission medium. The transmission medium participates in the transfer of information between the storage media. For example, the transmission medium includes coaxial cables, copper wires, and optical fibers, including the wires that make up a 920 I / O subsystem bus. The transmission means can also take the form of acoustic or light waves, such as those generated during data communications by radio and infrared waves.

[0183] Various means may be involved in transporting at least one sequence of at least one instruction to the processor 910 for execution. For example, the instructions may first be loaded onto a magnetic disk or a solid-state disk of a remote computer. The remote computer may load the instructions into its dynamic memory and send the instructions over a communication link such as a fiber optic or coaxial cable or a telephone line using a modem. A modem or router local to the computer system 905 may receive the data over the communication link and convert the data into a format that can be read by the computer system 905.For example, a receiver such as a radio frequency antenna or an infrared detector can receive data carried in a wireless or optical signal, and a suitable circuit can provide the data to an I / O subsystem 920, for example, by placing the data on a bus. The I / O subsystem 920 carries the data to memory 925, from which the processor 910 retrieves and executes instructions. Instructions received by memory 925 can optionally be stored on storage unit 915 before or after execution by the processor 910.

[0184] The computer system 905 also includes a communication interface 960 coupled to the bus 920. The communication interface 960 provides bidirectional data communication coupling to the network link(s) 965 that are directly or indirectly connected to at least one communication network, such as a network 970 or a public or private cloud on the Internet. For example, the communication interface 960 may be an Ethernet network interface, an Integrated Services Digital Network (ISDN) card, a cable modem, a satellite modem, or a modem for providing a data communication connection to a corresponding type of communication line, for example, an Ethernet cable, a metallic cable of any kind, a fiber optic line, or a telephone line. The network 970 broadly represents a local area network (LAN), a wide area network (WAN), a campus network, an internetwork, or any combination thereof.The 960 communication interface may include a LAN card to provide a data communication connection to a compatible local area network, or a wired cellular radiotelephone interface to send or receive cellular data according to cellular radiotelephone wireless network standards, or a wired satellite radio interface to send or receive digital data according to satellite wireless network standards. In such an implementation, the 960 communication interface sends and receives electrical, electromagnetic, or optical signals via signal paths that carry digital data streams representing various types of information.

[0185] The network link 965 generally provides electrical, electromagnetic, or optical data communication directly or through at least one network to other data devices, using, for example, satellite, cellular, Wi-Fi, or Bluetooth technology. For example, the network link 965 can provide a connection through a network 970 to a host computer 950.

[0186] In addition, the network link 965 can provide a connection via the network 970 or to other computing devices via network interconnect devices and / or computers that are operated by an Internet Service Provider (ISP) 975. LTSP 975 provides data communication services via a global packet-switched data communication network represented by the Internet 980. A server computer 955 can be coupled to the Internet 980. The server 955 broadly represents any computer, data center, virtual machine or virtual computing instance with or without a hypervisor, or computer running a containerized program system such as Docker or Kubernetes. The server 955 can represent an electronic digital service that is implemented using multiple computers or instances and is accessed and used by transmitting web service requests, URL strings (Uniform Resource Locator) with parameters in HTTP payloads, API calls, application service calls, or other service calls. The 905 computer system and the 955 server can be part of a distributed computing system that includes other computers, a processing cluster, a server farm, or another organization of computers that cooperate to perform tasks or run applications or services. The 955 server can have one or more sets of instructions organized into modules, processes, objects, functions, routines, or calls. The instructions can be organized into one or more computer programs, operating system services, or application programs, including mobile applications. Instructions may include an operating system and / or system software; one or more libraries to support multimedia, programming, or other functions; instructions or data protocol stacks to implement TCP / IP, HTTP, or other communication protocols; file format processing instructions to parse or render files encoded in HTML, XML, JPEG, MPEG, or PNG; user interface instructions to render or interpret commands for a graphical user interface (GUI), a command-line interface, or a text-based user interface; application software such as an office suite, Internet access applications, design and manufacturing applications, graphics applications, audio applications, software engineering applications, educational applications, games, or miscellaneous applications.The 955 server may include a web application server that hosts a presentation layer, an application layer, and a data storage layer such as a relational database system using a structured query language (SQL) or without SQL, an object store, a graph database, a flat file system, or another data storage unit.

[0187] The computer system 905 can send messages and receive data and instructions, including program code, via the network(s), the network link 965, and the communication interface 960. In the Internet example, a server 955 can transmit requested code for an application program via the Internet 980, ISP 975, local area network 970, and communication interface 960. The received code can be executed by the processor 910 when received and / or stored in the storage unit 915, or another non-volatile storage unit for later execution.

[0188] The execution of instructions as described in this section may implement a process in the form of an instance of a computer program that is executed and consists of program code and its ongoing activity. Depending on the operating system (OS), a process can be composed of multiple threads that execute instructions simultaneously. In this context, a computer program is a passive set of instructions, while a process can be the actual execution of those instructions. Multiple processes can be associated with the same program; for example, opening multiple instances of the same program often means that multiple processes are running. Multitasking can be implemented to allow multiple processes to share the 910 processor. While each 910 processor or processor core executes a single task at a time, the 905 computer system can be programmed to implement multitasking to allow each processor to switch between running tasks without having to wait for each task to finish.In one embodiment, failovers can occur when tasks perform input / output operations, when a task indicates that a failover is possible, or during hardware interrupts. Time-sharing can be implemented to enable fast response times for interactive user applications by rapidly performing context switches to provide the appearance of concurrent execution of multiple processes simultaneously. In one embodiment, for security and reliability reasons, an operating system can prevent direct communication between independent processes, providing strictly mediated and controlled interprocess communication functionality.

[0189] Object of the invention

[0190] The present invention is intended to remedy all or part of the drawbacks of the prior art.

[0191] To this end, according to a first aspect, the present invention relates to a predictive maintenance system for aquatic installations, comprising: - at least one physical / chemical sensor interacting with water in at least one aquatic installation and configured to provide a series of at least one detected value representative of a physical / chemical parameter, and - at least one processor configured to execute instructions representative of the following steps: - operation of a trained machine learning model, said model being trained to associate, for at least a series of detected values ​​representative of a physical / chemical parameter, at least one operational degradation event of an aquatic installation with a date of occurrence of the event, and - determination of a sequence of maintenance operations to be carried out on at least one aquatic installation as a function of at least one degradation event operational aquatic installation planned and the associated date of occurrence of the event.

[0192] These provisions make it possible both to accurately predict a future maintenance need for one or more aquatic installations and to optimize the sequence of maintenance operations in order to reduce the short- and long-term risks of lasting degradation of the installation or the water it contains.

[0193] In particular embodiments, the system of the present invention comprises a submersible and / or floating vehicle, including at least one said physical / chemical sensor and / or a conduit of a circulation system through which water flows, and / or in an analysis chamber including at least one said physical / chemical sensor, configured to provide a measurement of a local physical / chemical parameter in the vicinity of the submersible and / or floating vehicle and / or in the circulation system of the aquatic installation.

[0194] Such arrangements make it possible to accurately determine the problems and risks associated with water in the installation and / or the installation itself. The possibility of using sensors mounted on a mobile vehicle allows for greater flexibility in positioning these sensors relative to a particular physical / chemical value to be analyzed. The correlation between positioning and measurement ensures greater accuracy of results and improved diagnostic capabilities.

[0195] In particular embodiments, the submersible and / or floating vehicle includes an optical sensor, configured to provide a graphical representation of the water and / or aquatic installation, said representation being used during the operating stage of the trained machine learning model.

[0196] In particular embodiments, at least one physical / chemical sensor may be: - a pH sensor, and / or - a total alkalinity sensor, and / or - a conductivity sensor, and / or - a redox potential sensor, and / or - a turbidity sensor, and / or - a temperature sensor, and / or - a flow sensor, and / or - an optical sensor, and / or - a camera and / or a video camera, and / or - an acoustic and / or sonar sensor, and / or - a water movement sensor, and / or - a pressure sensor.

[0197] In particular embodiments, at least one physical / chemical sensor is a device for measuring total aquatic alkalinity, comprising: - a pH probe configured to measure the pH at the boundary layer of a body of water, - Optionally, a floating reference device near the pH probe, - a sensor controller, configured to sequentially activate and deactivate, or connect and disconnect, the pH probe. - a pH measurement variation detection device, configured to detect a pH measurement variation in a sequence of pH probe measurements, and - a device for determining the value of total aquatic alkalinity, configured to determine a value of total aquatic alkalinity of the water mass as a function of the detected pH measurement variation.

[0198] Such arrangements allow for a precise and virtually real-time measurement of the total alkalinity of a body of water at an affordable cost and with ordinary equipment. However, the advantages of the present invention result from the inventors' counterintuitive discovery that switching the pH probe on and off when the water is not flowing provides a precise measurement of the total alkalinity, whereas continuous pH measurement does not. Indeed, the successive activation / deactivation or connection / disconnection of the pH probe causes a chemical reaction in the vicinity of the pH probe. This chemical reaction results in a change in the pH measurement, said change depending on the total alkalinity of the water near the deactivated pH probe when the water is not flowing.Therefore, the present invention makes it possible to determine the total alkalinity value of a body of water without using a total alkalinity sensor. Such an indirect measurement significantly improves the ability to measure total alkalinity in aquatic facilities and in any other water storage and management system.

[0199] In particular embodiments, the system object of the present invention comprises an external parameter sensor, the trained model being configured to associate, for at least one series of detected values ​​representative of a physical / chemical parameter and at least one series of detected external parameters, at least one operational degradation event of an aquatic installation with a date of occurrence of the event.

[0200] Such embodiments allow the machine learning model to be trained to recognize patterns that involve external parameters, such as weather, air pollution, the number of bathers in the aquatic facility, the acquisition of external images or air temperature, for example.

[0201] In particular embodiments, at least one processor is configured to execute instructions representative of an assignment step, for at least one event planned in a sequence of maintenance operations, of an operator identifier according to the operator parameters associated with the operator identifier.

[0202] Such embodiments allow for the dynamic and efficient allocation of human resources to the maintenance of the aquatic installation.

[0203] In particular embodiments, at least two operator identifiers are assigned during the assignment step, at least one processor being configured to execute instructions representative of the following steps: - transmission, to a third-party computer system associated with a user identifier, of at least two of said operator identifiers, and - receipt, from a third-party computer system associated with the user identifier, of a selection of at least one of at least two of said operator identifiers.

[0204] Such embodiments allow a managing user to select the operator in charge of maintenance. Such a selection can be based on financial cost, distance, or the operator's experience, for example.

[0205] In particular embodiments, at least one expected event is associated with an event type identifier, at least one operator parameter representing operator-event type identifier compatibility.

[0206] Such embodiments allow the selection, by a managing user, of the operator in charge of maintenance on the basis of the compatibility (expertise) of said operator with the planned maintenance event.

[0207] In particular embodiments, at least one processor is configured to execute instructions representative of a step of identifying at least one product identifier representative of a product to be used during the determined sequence of maintenance operations.

[0208] Such embodiments make it possible to identify products that can mitigate the severity of the planned maintenance event or allow the maintenance to be completed.

[0209] In particular embodiments, at least two product identifiers are identified during the identification step, with at least one processor configured to execute instructions representative of the following steps: - transmission, to a third-party computer system associated with a user ID, of at least two of said product IDs, and - receipt, from a third-party computer system associated with the user ID, of a selection of at least one of at least two of said product IDs.

[0210] Such embodiments allow a managing user to select the product to be used for maintenance. Such a selection can be based on financial cost, distance, or product quality, for example.

[0211] In particular embodiments, at least one processor is configured to execute instructions representative of a step for estimating a product impact index, representative of the ability of a product to resolve an operational degradation event of an aquatic facility, said index being associated with at least one product identifier identified and transmitted during the transmission step.

[0212] Such embodiments allow a managing user to select the product to be used for maintenance based on the probability of the product having a positive impact on the planned maintenance event.

[0213] In particular embodiments, at least one processor is configured to execute instructions representative of a transmission step, to a third-party computer system associated with at least one selected product identifier, of a message representative of a purchase order for at least one product associated with at least one selected product identifier.

[0214] Such embodiments allow for the automatic acquisition of the selected product and shipment to the aquatic facility.

[0215] In particular embodiments, at least one physical / chemical sensor is associated with geographic coordinates, the sequence determination step being configured to further determine a sequence based on the geographic coordinates of aquatic facilities associated with at least one planned aquatic facility operational degradation event.

[0216] Such embodiments allow for a dynamic and efficient allocation of operators and resources to optimize the logistics of said resources.

[0217] According to a second aspect, the present invention relates to a predictive maintenance method for aquatic installations, comprising: - at least one operating step of a physical / chemical sensor interacting with water in at least one aquatic installation to provide a series of at least one detected value representative of a physical / chemical parameter, - a step in the operation of a trained machine learning model, said model being trained to associate, for at least one series of detected values ​​representative of a physical / chemical parameter, at least one operational degradation event of an aquatic facility with a date of occurrence of the event, and - a step of determining a sequence of maintenance operations to be carried out on at least one aquatic installation based on at least one event of planned operational degradation of aquatic facility and the date of occurrence of the associated event.

[0218] The process of the present invention offers the same advantages as the system of the present invention.

Claims

Demands

1. Predictive maintenance system for aquatic installations (100), characterized in that it comprises: - at least one physical / chemical sensor (110, 115, 116, 117, 181, 182, 183, 184) interacting with the water in at least one aquatic installation and configured to provide a series of at least one detected value representative of a physical / chemical parameter, said physical / chemical sensor being an aquatic total alkalinity measuring device (500), comprising: - a pH probe, configured to measure the pH at the boundary layer of a body of water, - a probe controller, configured to sequentially activate and deactivate, or connect and disconnect, the pH probe, - a pH measurement variation detection device, configured to detect a pH measurement variation in a sequence of measurements by pH probe, and - an aquatic total alkalinity value determination device.configured to determine a total aquatic alkalinity value for the water body based on the variation in the detected pH measurement, and - at least one processor (120) configured to execute instructions representative of the following steps: - operation of a trained machine learning model, said model being trained to associate, for at least a series of detected values ​​representative of a physical / chemical parameter, at least one aquatic facility operational degradation event with a date of occurrence of the event, and - determination of a sequence of maintenance operations to be performed on at least one aquatic facility based on at least one anticipated aquatic facility operational degradation event and the associated date of occurrence of the event.

2. A system (100) according to claim 1, comprising a submersible and / or floating vehicle (105, 106), including at least one said physical / chemical sensor (110, 115, 116, 117) and / or a conduit of a circulation system through which water flows, and / or an analysis chamber (180) comprising at least one said physical / chemical sensor (181, 182, 183, 184), configured to provide a measurement of a local physical / chemical parameter in the vicinity of the submersible and / or floating vehicle and / or in the circulation system of the aquatic installation.

3. System (100) according to claim 2, wherein the submersible and / or floating vehicle (105, 106) comprises an optical sensor (115), configured to provide a graphical representation of the water and / or aquatic installation, said representation being used during the operating step of the trained machine learning model.

4. System (100) according to any one of claims 1 to 3, wherein at least one physical / chemical sensor (110, 115, 116, 117) is: - a pH sensor, and / or - a total alkalinity sensor, and / or - a conductivity sensor, and / or - a redox potential sensor, and / or - a turbidity sensor, and / or - a temperature sensor, and / or - a flow sensor, and / or - an optical sensor, and / or - a camera and / or a video camera, and / or - an acoustic and / or sonar sensor, and / or - a water movement sensor, and / or - a pressure sensor.

5. System (100) according to any one of claims 1 to 4, comprising an external parameter sensor (118), the trained model being configured to associate, for at least one series of detected values ​​representative of a physical / chemical parameter and at least one series of detected external parameters, at least one aquatic facility operational degradation event with an event occurrence date.

6. System (100) according to any one of claims 1 to 5, wherein at least one processor (120) is configured to execute instructions representative of an assignment step, for at least one event expected in a sequence of maintenance operations, of an operator identifier based on the operator parameters associated with the operator identifier.

7. System (100) according to claim 6, wherein at least two operator identifiers are assigned during the assignment step, at least one processor (120) being configured to execute instructions representative of the following steps: - transmission, to a third-party computer system associated with a user identifier, of at least two of said operator identifiers and - reception, from a third-party computer system associated with the user identifier, of a selection of at least one of the at least two of said operator identifiers.

8. System (100) according to claim 6 or 7, wherein at least one expected event is associated with an event type identifier, at least one operator parameter representing operator-event type identifier compatibility.

9. System (100) according to any one of claims 1 to 8 wherein at least one processor (120) is configured to execute instructions representative of a step of identifying at least one product identifier representative of a product to be used during the determined sequence of maintenance operations.

10. System (100) according to claim 9, wherein at least two product identifiers are identified during the identification step, at least one processor (120) being configured to execute instructions representative of the following steps: - transmission, to a third-party computer system associated with a user identifier, of at least two of said product identifiers and - reception, from a third-party computer system associated with the user identifier, of a selection of at least one of the at least two of said product identifiers.

11. System (100) according to claim 10, wherein at least one processor (120) is configured to execute instructions representative of a step of estimating a product impact index, representative of the ability of a product to resolve an operational degradation event of an aquatic facility, said index being associated with at least one product identifier identified and transmitted during the transmission step.

12. System (100) according to any one of claims 10 or 11, wherein at least one processor (120) is configured to execute instructions representative of an issuance step, to a third-party computer system associated with at least one selected product identifier, of a message representative of a purchase order for at least one product associated with at least one selected product identifier.

13. System (100) according to any one of claims 1 to 12, wherein at least one physical / chemical sensor (110, 115, 116, 117, 118, 181, 182, 183, 184) is associated with geographic coordinates, the sequence determination step being configured to further determine a sequence based on the geographic coordinates of aquatic facilities associated with at least one anticipated aquatic facility operational degradation event.

14. A predictive maintenance method for an aquatic installation (200), characterized in that it comprises: - at least one step (205) of operating a physical / chemical sensor interacting with water in at least one aquatic installation to provide a series of at least one detected value representative of a physical / chemical parameter, said physical / chemical sensor being a device for measuring total aquatic alkalinity, comprising: - a pH probe, configured to measure the pH at the boundary layer of a body of water, - a probe controller, configured to sequentially activate and deactivate, or connect and disconnect, the pH probe, - a device for detecting a variation in pH measurement, configured to detect a variation in pH measurement within a sequence of measurements by pH probe, and - a device for determining the value of total aquatic alkalinity.configured to determine a total aquatic alkalinity value of the water mass as a function of the variation in the detected pH measurement, - a step (210) of operation of a trained machine learning model, said model being trained to associate, for at least one series of detected values ​​representative of a physical / chemical parameter, at least one aquatic facility operational degradation event with an event occurrence date and, - a step (215) of determining a sequence of maintenance operations to be carried out on at least one aquatic installation based on at least one planned aquatic installation operational degradation event and the associated date of occurrence of the event.

Images